In the last few years, natural language processing and computer vision have experienced a fundamental shift in the way these fields use machine learning. Rather than training neural networks from a randomly initialized set of parameters, researchers have often found superior performance can be achieved by fine-tuning a general pre-trained “foundation model” trained on vast amounts of diverse data - perhaps because this model comes with better “priors” than an untrained network. Polymathic AI[1] is a new research collaboration that aims to usher in the same shift in machine learning for scientific datasets. In this talk I will present the motivations behind the collaboration and describe the findings of our three new papers in this space, which examine: better numerical encodings for large language models[2], contrastive embeddings for multi-modal scientific data[3], and building machine learning models that learn from multiple types of physics[4].
1 polymathic-ai....
2 arxiv.org/abs/...
3 arxiv.org/abs/...
4 arxiv.org/abs/...
Bio: Miles Cranmer is Assistant Professor in Data Intensive Science, DAMTP & Institute of Astronomy, University of Cambridge. Website: astroautomata....
Agenda: indico.cern.ch...
Check out A3D3 Institute and seminar series: a3d3.ai/
Subscribe to receive new announcement of talks
Subscribe here ► groups.google....
Негізгі бет A3D3 seminar: Polymathic AI: Foundation Models for Science by Miles Cranmer
Пікірлер: 2